• Principal investigator: Jin Lee
• Advisor: Professor Seung Wan Hong, Inha Univ.

This study is interdisciplinary research based on the intersection of the three circles: (1) Architectural Design, (2) Reinforcement-Learning Powered Agent-based Simulation, and (3) Children’s Learning Environment. A comparative experiment is conducted with fourteen professional architects to investigate the empirical effects of the RL agents-powered simulation. The participants produced fourteen children’s learning environment designs using habitual design methods (without simulation) and the children’s play behavior simulation model (with simulation). 

Based on the interview with the survey and recorded video data,  the study analyzed the experiment design results in terms of (1) design trade-offs, (2) motivation, and (3) quantifiable performance. Eventually, the study found that the RL-powered agent-based simulation enables the architects to shift their perspective from adult to child-centric and ultimately optimize holistic design performance.

In the first section, the participants performed the kindergarten design task with their habitual methods, including 3D modeling, diagramming, and sketching. In the second section, they explored their initial design using the simulation and modified it based on the observation. In the experiments, the designers and the operators were separated to let the participants focus on their design processes. 

Epilogue: self-congratulations on awarding the Grand Prize at the 2023 Best Thesis Award hosted by the Architectural Institute of Korea. Here is the panel presentation, exhibited for the awards.